Related papers: Object Capabilities and Lightweight Affinity in Sc…

Conformer has shown a great success in automatic speech recognition (ASR) on many public benchmarks. One of its crucial drawbacks is the quadratic time-space complexity with respect to the input sequence length, which prohibits the model to…

We introduce a novel parsing concept called local lexing. It integrates the classically separated stages of lexing and parsing by allowing lexing to be dependent upon the parsing progress and by providing a simple mechanism for constraining…

Automata learning is a technique that has successfully been applied in verification, with the automaton type varying depending on the application domain. Adaptations of automata learning algorithms for increasingly complex types of automata…

Open-vocabulary object detection has benefited greatly from pretrained vision-language models, but is still limited by the amount of available detection training data. While detection training data can be expanded by using Web image-text…

Scaling the amount of data used for supervied fine-tuning(SFT) does not guarantee the proportional gains in model performance, highlighting a critical need to understand what makes training samples effective. This work identifies two…

Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…

In this report, we explore the ability of language model agents to acquire resources, create copies of themselves, and adapt to novel challenges they encounter in the wild. We refer to this cluster of capabilities as "autonomous replication…

Active learning (AL) for real-world object detection faces computational and reliability challenges that limit practical deployment. Developing new AL methods requires training multiple detectors across iterations to compare against…

Speech processing systems currently do not support the vast majority of languages, in part due to the lack of data in low-resource languages. Cross-lingual transfer offers a compelling way to help bridge this digital divide by incorporating…

The AgentSpeak type of languages are considered for decision making in autonomous control systems. To reduce the complexity and increase the verifiability of decision making, a limited instruction set agent (LISA) is introduced. The new…

Contrastive language-audio pretraining (CLAP) has achieved notable success in learning semantically rich audio representations and is widely adopted for various audio-related tasks. However, current CLAP models face several key limitations.…

Large language models (LLMs) have proven to work well in question-answering scenarios, but real-world applications often require access to tools for live information or actuation. For this, LLMs can be extended with tools, which are often…

Recent methods for long-tailed instance segmentation still struggle on rare object classes with few training data. We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data…

Voice cloning is a prominent feature in personalized speech interfaces. A neural vocal cloning system can mimic someone's voice using just a few audio samples. Both speaker encoding and speaker adaptation are topics of research in the field…

Understanding how language model performance varies with scale is critical to benchmark and algorithm development. Scaling laws are one approach to building this understanding, but the requirement of training models across many different…

Recent advances in crowd counting have achieved promising results with increasingly complex convolutional neural network designs. However, due to the unpredictable domain shift, generalizing trained model to unseen scenarios is often…

Progress in object detection benchmarks is stagnating. It is limited not by architectures but by the inability to distinguish model improvements from label noise. To restore trust in benchmarking the field requires rigorous quantification…

Recent instruction-finetuned large language models (LMs) have achieved notable performances in various tasks, such as question-answering (QA). However, despite their ability to memorize a vast amount of general knowledge across diverse…

Large-scale pre-trained image-text models demonstrate remarkable versatility across diverse tasks, benefiting from their robust representational capabilities and effective multimodal alignment. We extend the application of these models,…

Audio-visual sound source localization task aims to spatially localize sound-making objects within visual scenes by integrating visual and audio cues. However, existing methods struggle with accurately localizing sound-making objects in…